• Join over 1.2 million students every month
  • Accelerate your learning by 29%
  • Unlimited access from just £6.99 per month

Analysis of Bivariate Data - I aim to investigate the relationship between score in the P1 mock paper and score in the P1 exam. My population is lower sixth students at Peter Symonds College.

Extracts from this document...


Aidan Russell-Gear                Page  of

S2 Coursework – Analysis of Bivariate Data


        I aim to investigate the relationship between score in the P1 mock paper and score in the P1 exam. My population is lower sixth students at Peter Symonds College; I have obtained a table of 304 students which tells me their maths A-level course, gender, average GCSE score, results in P1 tests 1 and 2, P1 mock and P1 exam, from the college maths department.

        I wish to investigate this relationship so that my results may be used in the future by teachers and students to assess whether it is fair to base a prediction of the likely P1 exam score on the P1 mock result. I hope this will prove useful in deciding future options and motivating students to self-improvement. I hope then to prove convincingly whether the P1 exam result is correlated with the P1 mock result, and to what extent is this correlation.

        From my population of 304 students I took a sample of 50 to analyse for ease of calculation, I obtained this group by a simple random sample method. I assigned a random number to each student, then sorted the data in descending order and took the first 50 students as my sample.

...read more.


Pearson’s product moment correlation coefficient:

        And so the value of r was found to be 0.798922, and we see this result is a strong indication of positive correlation. However, this is merely my informed opinion, in order to get a more definitive answer to whether these two variables are correlated we must perform a hypothesis test.

Hypothesis Test

        To do this I must use the tables of critical values found in the MEI student handbook. These are standard pre-calculated values which will indicate whether or not my data are correlated, again assuming random normal distribution.

        My starting hypothesis, the null hypothesis (H0), is that there is no correlation between the P1 mock and P1 result in the population at all, my second (H1) is that there is some positive correlation. It is clear that there is no negative correlation and so I can merely look at the probabilities of positive correlation. I will perform a hypothesis test against the correlation coefficient of the parent population, ρ, my value of r is an estimate to ρ taken from a sample of the parent population.

                H0:        ρ = 0

                H1:        ρ > 0

...read more.


Note that my population was only from one year at Peter Symonds College and students could vary from year to year, though this is unlikely to be significant. However when performing the hypothesis test I assumed that my correlation coefficient was a good estimate for ρ, the parent correlation coefficient, and this was central to the validity of the hypothesis testing as a method of analysis. I feel that this is acceptable due to the high nature of the calculated correlation coefficient compared to the critical values for ρ calculated at 5% and at 0.5%, thus I feel that any error can be accommodated by the significantly larger value of the calculated coefficient than the critical value. This difference is so large that I am convinced of the validity of the relationship.


        The following sources were used in my in my investigation:

MEI Structured Mathematics – Statistics 2 (second edition)

MEI Structured Mathematics – Students’ Handbook

...read more.

This student written piece of work is one of many that can be found in our AS and A Level Probability & Statistics section.

Found what you're looking for?

  • Start learning 29% faster today
  • 150,000+ documents available
  • Just £6.99 a month

Not the one? Search for your essay title...
  • Join over 1.2 million students every month
  • Accelerate your learning by 29%
  • Unlimited access from just £6.99 per month

See related essaysSee related essays

Related AS and A Level Probability & Statistics essays

  1. Data Handling - Planning - I intend to investigate the relationship between the number ...

    This is known as the interquartile range. Interquartile range = upper quartile - lower quartile Interquartile range is an important measure of spread. It shows how widely the data is spread. If the interquartile range is small, the middle half of the distribution is bunched together.

  2. Intermediate Maths Driving Test Coursework

    I think Instructor C however is better than A or B so far in teaching both male and female as they both had the lowest mistakes. From this graph we can see a fairly strong negative correlation however it is a gentle slope of a line ad very high up despite high amount of lessons.

  1. Anthropometric Data

    shows that all the points lie generally on an upward diagonal and also shows that there is an outlier. Outlier An outlier can occur due the basic linear relationship between (x) and (y), a single outlier occur in the (x)

  2. The aim of this investigation was to look at the reliability and validity of ...

    For a trait theory to be acceptable as a personality theory it must firstly isolate basic traits which describe personality and measure them accurately. This is attempted using a process called Factor Analysis. A pioneer in this field was Raymond Cattell (1965).

  1. Design an investigation to see if there is a significant relationship between the number ...

    As well as having experienced the optimum conditions over the summer months, genetic variation within the species should also mean that the Fucus Vesiculosus are best adapted to live on the shore, and therefore they should be thriving. Genetic variation is caused by mutations in certain of the seaweeds' genes, which are passed on to the offspring during reproduction.

  2. Guestimate - investigate how well people estimate the length of lines and the size ...

    I will plot the estimates, as these will show me the modal group for each year. I used two methods to work out the class width and the frequency density, they were: Class width = upper boundary - lower boundary and Frequency density = frequency Class width Year 7 Class (degrees)

  1. Is there a Correlation between GCSE Mathematics and English Literature scores?

    I decided that random sampling would be the best sampling method so as to keep my sample as representative and unbiased as possible. I arranged the names of these pupils in alphabetical order and then issued each pupil with a number.

  2. Driving test

    There are more males students that "passed comfortably" compared to females. There are a greater number of females that "just passed" compared to males. In total, 23 females passed and only 21 males passed. For both genders, 8 people failed.

  • Over 160,000 pieces
    of student written work
  • Annotated by
    experienced teachers
  • Ideas and feedback to
    improve your own work